Prediction of engine performance, combustion and emission for canola oil biodiesel blends using artificial neural network

Yıl 2019, Cilt: 7 Sayı: 3, 2045 - 2056, 31.07.2019

Mehmet Şen

https://doi.org/10.29130/dubited.551230

Cited By: 2

Öz

In this study, the results of emission, performance and combustion
experimental data of diesel fuel and canola oil biodiesel blends used in a
diesel engine and the results of the model created by artificial neural
networks were compared. For construct the model 44 different engine test
results were used. The feedback algorithm was used in the training of the
network. The trainlm was selected as the learning algorithm. The logsig function
was used in the hidden layer while the purelin function was used in the output
layer. The input variables in network training were fuel blend ratios, engine
speeds and engine loads. At the output of network a separate model was created
for each of the specific fuel consumption, exhaust temperature, combustion
efficiency, start of injection, start of combustion, ignition delay, combustion
duration, smoke opacity and NO_x values. The R² values of
the ANN models were calculated to be higher than 0.99 for the performance and
combustion parameters and higher than 0.98 for the emissions value.

Anahtar Kelimeler

Keywords: ANN, emission, combustion, performance

Yapay Sinir Ağı Kullanarak Kanola Yağı Biyodizel Karışımları İçin Motor Performansı, Yanma ve Emisyon Tahmini

Öz

Bu
çalışmada bir dizel motorda kullanılan dizel yakıtı ve kanola yağından üretilen
biyodizel karışımlarının; emisyon, performans ve yanma deneysel verileri ile
yapay sinir ağları ile oluşturulan modelin sonuçları karşılaştırılmıştır.
Modelin oluşturulması için 44 farklı motor deney sonuçları kullanılmıştır. Ağın
eğitiminde geri beslemeli algoritma kullanılmıştır. Öğrenme algoritması olarak
trainlm, gizli katmanda logsig ve çıkış katmanında ise purelin fonksiyonları
kullanılmıştır. Ağ eğitiminde
giriş değişkenleri: karışımdaki dizel yakıt oranı, kanola yağı biyodizel oranı,
motor devri ve motor momentidir. Çıkışta ise özgül yakıt tüketimi (ÖYT), egzoz
sıcaklığı, yanma verimi, püskürtme başlangıcı, yanma başlangıcı, tutuşma
gecikmesi, yanma süresi, duman koyuluğu ve NOx değerlerinin her biri için ayrı
model oluşturulmuştur. YSA modellerinin R² değerleri tutuşma
gecikmesi için 0,998, yanma süresi için 0,992, duman koyuluğu için 0,984, NOx
için ise 0,990 olarak hesaplanmıştır. R² değerleri ÖYT, egzoz
sıcaklığı, yanma verimi, püskürtme başlangıcı ve yanma başlangıcı değerleri
için ise 0,999‘dan yüksek bulunmuştur.

Anahtar Kelimeler

YSA, emisyon, yanma, performans

Kaynakça

• [1] A.O. Emiroğlu, A. Keskin and M. Şen, “Experimental investigation of the effects of turkey rendering fat biodiesel on combustion, performance and exhaust emissions of a diesel engine,” Fuel, c. 216, pp. 266–273, 2018.
• [2] A. Keskin, “Pamuk yağı metil esteri-eurodizel yakıt karışımlarının direkt püskürtmeli bir dizel motorunun yanma, performans ve emisyon karakteristiklerine etkisi,” Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, c. 18, s. 2, ss. 1–18, 2018.
• [3] M. Şen, A.O. Emiroğlu, and A. Keskin, “Production of biodiesel from broiler chicken rendering fat and investigation of its effects on combustion, performance, and emissions of a diesel engine,” Energy & fuels, vol. 32, no. 4, pp. 5209–5217, 2018.
• [4] A. Keskin, “Two-step methyl ester production and characterization from the broiler rendering fat: The optimization of the first step,” Renewable Energy, vol. 122, pp. 216–224, 2018.
• [5] A. Keskin, “Pamuk Yağı Biyodizeli-Eurodizel Karışımlarının Tam Yükte Yanma, Performans ve Emisyonlara Etkisinin Deneysel Olarak İncelenmesi,” Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, c. 17, s. 2, ss. 797-809, 2017.
• [6] S. Sarıdemir ve S. Albayrak, “Kanola yağı metil esteri ve karışımlarının motor performans ve egzoz emisyonlarına olan etkileri,” İleri Teknoloji Bilimleri Dergisi, c. 4, s. 1, ss. 35-46, 2015
• [7] S. Sarıdemir ve M. Tekin, “Kanola Yağı Metil Esteri ve Dizel Yakıt Karışımlarının Tek Silindirli Dizel Bir Motorun Performans ve Gürültü Emisyonlarına Etkisi,” Politeknik Dergisi, c. 19, s. 1, ss. 53-59, 2016.
• [8] S. Ozturk, “Application of the Taguchi method for surface roughness predictions in the turning process,” Materials Testing, vol. 58, no. 9, pp. 782-787, 2016.
• [9] S. Ozturk, “Application of ANOVA and Taguchi Methods for Evaluation of the Surface Roughness of Stellite-6 Coating Material,” Materials Testing, vol. 56, no. 11-12, pp. 1015-1020, 2014.
• [10] F. Kara, “Taguchi optimization of surface roughness and flank wear during the turning of DIN 1.2344 tool steel,” Materials Testing, vol. 59, no. 10, pp. 903-908, 2017.
• [11] S. Ozturk, “Machinability of stellite-6 coatings with ceramic inserts and tungsten carbide tools,” Arabian Journal For Science And Engineering, vol. 39, no. 10, pp. 7375-7383, 2014.
• [12] B. Ghobadian, H. Rahimi, A.M. Nikbakht, G. Najafi and T.F. Yusaf, “Diesel engine performance and exhaust emission analysis using waste cooking biodiesel fuel with an artificial neural network,” Renewable Energy, vol. 34, pp. 976-982, 2009.
• [13] S. Uslu and M.B. Çelik, “Prediction of engine emissions and performance with artificial neural networks in a single cylinder diesel engine using diethyl ether,” Engineering Science and Technology, vol. 21, no. 6, pp. 1194-1201, 2018.
• [14] F. Kara, K. Aslantas and A. Çiçek, “ANN and multiple regression method-based modelling of cutting forces in orthogonal machining of AISI 316L stainless steel,” Neural Computing and Applications, vol. 26, no. 1, pp. 237-250, 2015.
• [15] B. Çırak and S. Demirtaş, “An application of artificial neural network for predicting engine torque in a biodiesel engine,” American Journal of Energy Research, vol. 2, no. 4, pp. 74-80, 2014.
• [16] Y. Çay, A. Çiçek, F. Kara and S. Sağıroğlu, “Prediction of engine performance for an alternative fuel using artificial neural network,” Applied Thermal Engineering, vol. 37, pp. 217-225, 2012.
• [17] Y.Ö. Özgören, S. Çetinkaya, S. Sarıdemir, A. Çiçek and F. Kara, “Artificial neural network based modelling of performance of a beta-type Stirling engine,” Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, vol. 227, no. 3, pp. 166-177, 2013.
• [18] Y.Ö. Özgören, S. Çetinkaya, S. Sarıdemir, A. Çiçek and F. Kara, “Predictive modeling of performance of a helium charged Stirling engine using an artificial neural network,” Energy conversion and Management, vol. 67, pp. 357-368, 2013.
• [19] M. Tekin and S. Saridemir, “Prediction of engine performance and exhaust emissions with different proportions of ethanol–gasoline blends using artificial neural networks,” International Journal of Ambient Energy, pp. 1-7, 2017.
• [20] T.F. Yusaf, D.R. Buttsworth, K.H. Saleh and B.F. Yousif, “CNG-diesel engine performance and exhaust emission analysis with the aid of artificial neural network,” Applied Energy, vol. 87, no. 5, pp. 1661-1669, 2010.
• [21] M. Canakci, A.N. Ozsezen, E. Arcaklioglu, A. Erdil, “Prediction of performance and exhaust emissions of a diesel engine fueled with biodiesel produced from waste frying palm oil,” Expert systems with Applications, vol. 36, no. 5, pp. 9268-9280, 2009.
• [22] A.O. Emiroğlu, M. Şen, “Combustion, performance and emission characteristics of various alcohol blends in a single cylinder diesel engine,” Fuel, vol. 212, pp. 34–40, 2018. [23] A.O. Emiroğlu, M. Şen, “Combustion, performance and exhaust emission characterizations of a diesel engine operating with a ternary blend (alcohol-biodiesel-diesel fuel),” Applied Thermal Engineering, vol. 133, pp. 371–380, 2018.
• [24] A.O. Emiroğlu, “Experimental examination of performance, exhaust emission and combustion behaviours of a CI engine fuelled with biodiesel/diesel fuel blends,” Sakarya University Journal of Science, vol. 22, no. 5, pp. 1274–1281, 2018.
• [25] M. Şen, “The influence of canola oil biodiesel on performance, combustion characteristics and exhaust emissions of a small diesel engine,” Sakarya University Journal of Science, vol. 23, no. 1, pp. 121-128, 2019.